home / skills / composiohq / awesome-claude-skills / appcircle-automation

appcircle-automation skill

safe

/appcircle-automation

This skill automates Appcircle tasks via Rube MCP, discovering current tool schemas first to ensure accurate execution.

npx playbooks add skill composiohq/awesome-claude-skills --skill appcircle-automation

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.9 KB

---
name: appcircle-automation
description: "Automate Appcircle tasks via Rube MCP (Composio). Always search tools first for current schemas."
requires:
  mcp: [rube]
---

# Appcircle Automation via Rube MCP

Automate Appcircle operations through Composio's Appcircle toolkit via Rube MCP.

**Toolkit docs**: [composio.dev/toolkits/appcircle](https://composio.dev/toolkits/appcircle)

## Prerequisites

- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active Appcircle connection via `RUBE_MANAGE_CONNECTIONS` with toolkit `appcircle`
- Always call `RUBE_SEARCH_TOOLS` first to get current tool schemas

## Setup

**Get Rube MCP**: Add `https://rube.app/mcp` as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

1. Verify Rube MCP is available by confirming `RUBE_SEARCH_TOOLS` responds
2. Call `RUBE_MANAGE_CONNECTIONS` with toolkit `appcircle`
3. If connection is not ACTIVE, follow the returned auth link to complete setup
4. Confirm connection status shows ACTIVE before running any workflows

## Tool Discovery

Always discover available tools before executing workflows:

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "Appcircle operations", known_fields: ""}]
session: {generate_id: true}
```

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

## Core Workflow Pattern

### Step 1: Discover Available Tools

```
RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Appcircle task"}]
session: {id: "existing_session_id"}
```

### Step 2: Check Connection

```
RUBE_MANAGE_CONNECTIONS
toolkits: ["appcircle"]
session_id: "your_session_id"
```

### Step 3: Execute Tools

```
RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"
```

## Known Pitfalls

- **Always search first**: Tool schemas change. Never hardcode tool slugs or arguments without calling `RUBE_SEARCH_TOOLS`
- **Check connection**: Verify `RUBE_MANAGE_CONNECTIONS` shows ACTIVE status before executing tools
- **Schema compliance**: Use exact field names and types from the search results
- **Memory parameter**: Always include `memory` in `RUBE_MULTI_EXECUTE_TOOL` calls, even if empty (`{}`)
- **Session reuse**: Reuse session IDs within a workflow. Generate new ones for new workflows
- **Pagination**: Check responses for pagination tokens and continue fetching until complete

## Quick Reference

| Operation | Approach |
|-----------|----------|
| Find tools | `RUBE_SEARCH_TOOLS` with Appcircle-specific use case |
| Connect | `RUBE_MANAGE_CONNECTIONS` with toolkit `appcircle` |
| Execute | `RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs |
| Bulk ops | `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` |
| Full schema | `RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef` |

---
*Powered by [Composio](https://composio.dev)*

Overview

This skill automates Appcircle tasks by orchestrating Composio’s Appcircle toolkit through a Rube MCP connection. It guides tool discovery, connection validation, and multi-tool execution while enforcing live schema checks and session handling. Use it to run builds, manage projects, and automate bulk operations against Appcircle with reliable schema-driven calls.

How this skill works

The skill first calls RUBE_SEARCH_TOOLS to discover available Appcircle tools and their exact input schemas. It then verifies or establishes an Appcircle connection via RUBE_MANAGE_CONNECTIONS and executes operations using RUBE_MULTI_EXECUTE_TOOL or RUBE_REMOTE_WORKBENCH, always supplying memory and session context. It enforces schema compliance, pagination handling, and session reuse for predictable workflows.

When to use it

Automate Appcircle build, deploy, or project management tasks
Run bulk operations or CI steps that require Appcircle APIs
When tool schemas may have changed and live discovery is required
Coordinate multi-step Appcircle workflows across sessions
Integrate Appcircle actions into broader Composio/Rube automation pipelines

Best practices

Always call RUBE_SEARCH_TOOLS first; never hardcode tool slugs or argument layouts
Verify connection status with RUBE_MANAGE_CONNECTIONS and complete any auth flow until ACTIVE
Pass memory (can be empty {}) in every RUBE_MULTI_EXECUTE_TOOL call
Reuse the same session_id for related steps; generate new session for new workflows
Check for pagination tokens in responses and fetch remaining pages as needed
Use RUBE_GET_TOOL_SCHEMAS for full schemas when schemaRef is provided

Example use cases

Discover Appcircle build and artifact tools, then trigger a build with schema-compliant arguments
Connect an Appcircle account, run project listing, and bulk-update project settings via RUBE_MULTI_EXECUTE_TOOL
Orchestrate a CI job: search tools, verify connection, run build, retrieve artifacts, and notify status
Use RUBE_REMOTE_WORKBENCH to run repeated composio_tool() tasks for large-scale bulk operations
Fetch tool schemas before generating inputs in an agent to avoid runtime errors

FAQ

What must I call before executing any tool?

Always run RUBE_SEARCH_TOOLS first to obtain current tool slugs and input schemas; tool shapes change frequently.

What if the Appcircle connection is not ACTIVE?

Call RUBE_MANAGE_CONNECTIONS for the appcircle toolkit and follow the returned auth link. Confirm the connection shows ACTIVE before proceeding.

Is memory required when executing tools?

Yes. Include a memory parameter in RUBE_MULTI_EXECUTE_TOOL calls even if it is empty ({}).

How should I handle long result sets?

Inspect responses for pagination tokens and iterate requests until all pages are retrieved.